Information processing systems, information processing methods, and programs

Abstract

We provide information processing systems and other tools that enable the overall optimization of the manufacturing line. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising a processor configured to perform the following steps by reading a program, wherein in the model acquisition step, a front-end model simulating a front-end process that produces an intermediate product from raw materials and a back-end model simulating a back-end process that produces a final product from the intermediate product are acquired; in the condition acquisition step, process conditions are acquired in the front-end model and the back-end model, respectively; and in the inference step, at least one of the characteristic values ​​of the intermediate product, the characteristic values ​​of the final product, the state values ​​of the equipment used in the front-end process, and the state values ​​of the equipment used in the back-end process are acquired as inferred values ​​by inputting the process conditions into a linked model in which at least the front-end model and the back-end model are linked.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses a system that optimizes production planning and logistics planning with a plurality of manufacturing processes as units of optimization.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above system, optimization can be achieved with the production cost as the objective function, but the cost of each manufacturing process is fixed independently of other processes. Therefore, there is room for improvement in the overall optimization of the manufacturing line.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that enables overall optimization of the manufacturing line.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising a processor configured to perform the following steps by reading a program, wherein in the model acquisition step, a front-end model simulating a front-end process that produces an intermediate product from raw materials and a back-end model simulating a back-end process that produces a final product from the intermediate product are acquired; in the condition acquisition step, process conditions are acquired in the front-end model and the back-end model, respectively; and in the inference step, at least one of the characteristic values ​​of the intermediate product, the characteristic values ​​of the final product, the state values ​​of the equipment used in the front-end process, and the state values ​​of the equipment used in the back-end process are acquired as inferred values ​​by inputting the process conditions into a linked model in which at least the front-end model and the back-end model are linked.

[0007] In this configuration, the entire manufacturing line can be optimized by adjusting the process conditions in the preceding and / or subsequent processes by referring to the inferred values ​​obtained from the linked model. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of the information processing device 10. [Figure 3] This is a block diagram showing the hardware configuration of user terminal 20. [Figure 4] This is a block diagram showing the functions realized by the information processing device 10 (control unit 11) and the user terminal 20 (control unit 21). [Figure 5] This diagram schematically illustrates the input and output of information in a linked model that combines the front-end and back-end process models. [Figure 6] This is an activity diagram showing an example of the flow of information processing (process condition adjustment processing) performed by information processing system 1. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0010] Incidentally, the program for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as "reference information") is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a pre-trained model that has learned the correlation between input and output in advance, or a large-scale language model that can output a desired result by inputting a prompt.

[0012] Furthermore, in one embodiment, "part" may include, for example, hardware resources implemented by a circuit in a broad sense, and the information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled, and this information can be represented, for example, by the physical values ​​of signal values ​​representing voltage and current, the high or low values ​​of signal values ​​as a set of binary bits composed of 0s or 1s, or by quantum superposition (so-called qubits), and communication and calculations can be performed on a circuit in a broad sense.

[0013] Furthermore, a circuit in a broad sense is a circuit realized by combining at least a suitable combination of circuits, circuits, processors, and memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes application-specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

[0014] 1. Hardware Configuration This section describes the hardware configuration.

[0015] <Information Processing System 1> Figure 1 is a configuration diagram representing information processing system 1. Information processing system 1 comprises a communication line 2, an information processing device 10, and a plurality of user terminals 20. The information processing device 10 and the user terminals 20 are configured to communicate with each other via the communication line 2. The connection between the information processing device 10 and the user terminals 20 may be wired or wireless.

[0016] In one embodiment of the information processing system 1, the information processing system 1 consists of one or more devices or components. These components will be described below.

[0017] <Information Processing Device 10> FIG. 2 is a block diagram showing the hardware configuration of the information processing apparatus 10. As shown in FIG. 2, the information processing apparatus 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected via the communication bus 14 inside the information processing apparatus 10.

[0018] <Control Unit 11> The control unit 11 performs processing and control of the overall operations related to the information processing apparatus 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 realizes various functions related to the information processing apparatus 10 by reading a predetermined program stored in the storage unit 12. That is, the information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the information processing apparatus 10 may have a plurality of control units 11 for each function. Further, the information processing apparatus 10 may have a configuration combining these.

[0019] <Storage Unit 12> The storage unit 12 stores various information defined by the foregoing description. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs and the like related to the information processing apparatus 10 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the calculation of programs. The storage unit 12 stores various programs, variables, etc. related to the information processing apparatus 10 executed by the control unit 11.

[0020] <Communication Unit 13> The communication unit 13 preferably uses wired communication methods such as USB, IEEE1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, the information processing device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The information processing device 10 may be on-premise or in a cloud-based configuration. In the case of a cloud-based information processing device 10, for example, the above-mentioned functions and processing may be provided in the form of SaaS (Software as a Service) or cloud computing.

[0022] <User terminal 20> The user terminal 20 is an information processing terminal used by users who utilize the manufacturing line optimization service provided by the information processing device 10. Figure 3 is a block diagram showing the hardware configuration of the user terminal 20. As shown in Figure 3, the user terminal 20 comprises a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, storage unit 22, communication unit 23, input unit 24, and output unit 25 are electrically connected within the user terminal 20 via the communication bus 26. The descriptions of the control unit 21, storage unit 22, and communication unit 23 are the same as the descriptions of each part in the information processing device 10 and are therefore omitted.

[0023] <Input section 24> The input unit 24 receives action input from the user. The action input is transmitted as a command signal to the control unit 21 via the communication bus 26. The control unit 21 can perform predetermined controls or calculations based on the transmitted command signal as needed. The input unit 24 may be included in the casing of the user terminal 20 or it may be external. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap actions, swipe actions, etc. to the input unit 24. Instead of a touch panel, the input unit 24 can be a switch button, mouse, trackpad, QWERTY keyboard, etc.

[0024] <Output section 25> The output unit 25 displays a graphical user interface (GUI) screen that allows the user to take action. The output unit 25 may be included in the casing of the user terminal 20 or it may be an external component. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used in accordance with the type of user terminal 20.

[0025] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (the processor provided by the information processing system 1).

[0026] Figure 4 is a block diagram showing the functions realized by the information processing device 10 (control unit 11) and the user terminal 20 (control unit 21).

[0027] As shown in Figure 4A, the information processing device 10 (control unit 11) includes a model registration unit 111, a model acquisition unit 112, a condition acquisition unit 113, an inference unit 114, a target acquisition unit 115, a condition adjustment unit 116, and an artificial intelligence unit 120. As shown in Figure 4B, the user terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212.

[0028] <Model Registration Section 111> The model registration unit 111 is configured to accept registration of production process models that simulate the process of generating the product. Specifically, the model registration unit 111 accepts uploads of production process models from the user terminal 20, input of the network storage location of the production process model from the user terminal 20, etc., and registers the model in the model database stored in the storage unit 12, for example.

[0029] The term "product generation process" refers to a production process in which raw materials are received and processed using equipment to obtain the desired product through chemical reactions, mechanical processing, etc. Specifically, the "product generation process" includes processes such as synthesis of multiple raw materials, dispersion of raw materials, mixing (kneading) of multiple raw materials, separation of specific components from raw materials, modification of raw materials, molding (casting) of raw materials, cutting of raw materials, painting of raw materials, dyeing of raw materials, surface processing (polishing, plating, thin film formation) of raw materials, attachment of other parts to raw materials, attachment of other parts to raw materials, and packaging of raw materials. Note that multiple types of raw materials may be introduced into a single production process. Also, multiple types of products may be obtained from a single production process.

[0030] A "production process model that simulates the process" is a numerical model that defines the correlation between input parameters representing the characteristics of raw materials and process conditions (equipment settings), and output parameters representing the characteristics of the product and the state of the equipment used in the process.

[0031] The input parameters, which are the characteristics of the raw materials, include, for example, the material properties (composition ratio, purity, quality), temperature distribution, stress distribution, volume, density, and shape of the raw materials. The input parameters, which are the process conditions, include, for example, the temperature, pressure, magnetic field, voltage (current), processing time, and processing sequence when performing processes such as chemical reactions and mechanical processing.

[0032] More specific process conditions include, for example, temperature sequence, partial pressure sequence, gas type switching timing, heating power supply output sequence, rotation sequence of each axis of the processing equipment, feed rate sequence of each axis, processing pressure sequence, equipment shape, material input amount, type of consumables and their physical properties before the process, cumulative number of uses of consumables before the process, cumulative number of uses of the equipment before the process, cumulative number of uses of the equipment after the latest maintenance, the installation environment of the equipment (temperature, humidity, etc.), and the processing position relative to the raw material.

[0033] The output parameters, which are the characteristics of the product, include, for example, temperature distribution, stress distribution, defect density distribution, shape (surface shape), and material composition ratio. The output parameters, which are the state of the equipment, include the temperature distribution (heat distribution) inside the equipment, pressure distribution (gas partial pressure distribution, gas flow velocity distribution), magnetic field distribution, type of consumables and their physical properties after process execution, cumulative number of uses of consumables after process execution, cumulative number of uses of the equipment after process execution, cumulative number of uses of the equipment after the latest maintenance, the installation environment of the equipment (temperature, humidity, etc.), degree of equipment deterioration, degree of consumable deterioration, degree of equipment contamination, time-series data (sensor values) such as temperature, gas flow rate, and current inside the equipment, electricity consumption, production speed, CO2 emissions, production cost, production variability, estimated maintenance timing for the equipment, and replacement timing for consumables.

[0034] A production process model is an estimator constructed to take input parameters as input and output parameters as output. A production process model may also be, for example, a table, function, or simple algorithm that shows the correlation between input and output parameters. The correlations included in a production process model can be constructed, for example, by statistically analyzing actual data from the production process that the model simulates.

[0035] The production process model may be a learned model that takes input parameters as input and outputs output parameters. In this case, the production process model is trained using combinations of input parameters and corresponding output parameters as training data. The parameters of the learned model calculated and tuned through such learning constitute the correlation of the production process model.

[0036] The production process model may also be a physical simulator (physics engine). In this case, the production process model takes the input parameters as initial conditions and outputs the results of the physical calculations performed on the raw materials for the processes included in the production process as output parameters.

[0037] The model registration unit 111 may register model information related to the production process model along with the production process model. The model information is input from the user terminal 20. The model information includes, for example, the dimensions (number of elements in the parameter) of the input parameters and output parameters, element information for each element of the input parameters and output parameters, metadata of the production process model, usage range information, etc.

[0038] Element information includes, for example, the element's name, numerical range (maximum and minimum values), numerical variation, units, significant figures, a flag indicating whether it can be adjusted (fixed value or not), and confidential information indicating whether it can be made public to other users.

[0039] Elements that contain a "not public" flag in their confidential information become confidential elements, and the specific numerical values ​​of these confidential elements are not disclosed to other users using the production process model (i.e., users other than the user who registered the production process model). Furthermore, if a confidential element is an input parameter, the confidential information includes information specifying one of the following adjustment methods for adjusting the numerical value of the confidential element: (1) or (2). (1) The values ​​of private elements are fixed and cannot be adjusted (the values ​​are not displayed to other users). (2) The numerical values ​​for private elements can be selected from pre-prepared options (numerical values ​​listed in the list). However, the options are displayed with labels such as "A", "B", and "C", and the numerical values ​​are not visible to other users.

[0040] The metadata includes information related to the construction of the production process model (learning curve, training data, hyperparameters, etc.). This includes the formulas, boundary conditions, approximation conditions, assumptions, and definitions of material properties used in the production process model.

[0041] The usage scope information includes information about other users who are permitted to use the production process model as part of the linked model of the inference unit 114, which will be described later. A production process model registered by a user is only permitted to be selected as an element of the manufacturing line (linked model) to be optimized by other users who are set as authorized users in the usage scope information.

[0042] The model registration unit 111 accepts registration of a first production process model that simulates the process of producing the product from the first user, and also accepts registration of a second production process model that simulates the process of producing the product from the second user. The second production process model is a model that simulates a different production process from the first production process model, for example, a model that simulates a process after the production process simulated by the first production process model. For example, in a manufacturing line for a certain product, the second user is a company that is responsible for the processes downstream from the first user.

[0043] The model registration unit 111 may accept updates from users for production process models that have already been registered. Specifically, the model acquisition unit 112 accepts input of an updated production process model from a user and replaces the production process model registered in the model database with the updated production process model.

[0044] Furthermore, the model registration unit 111 registers the configuration information of the linked model in the model database as information indicating a manufacturing line in which multiple production process models are linked. The linked model is a model that simulates a manufacturing line that includes multiple production processes. The registration of the configuration information of the linked model is performed, for example, by the user selecting the multiple production process models that constitute the manufacturing line to be optimized on the user terminal 20 in the order of the processes.

[0045] The model registration unit 111 receives information from the user terminal 20 that identifies the selected multiple production process models (model name, ID, etc.) and information indicating the order of the processes, and registers them in the model database as configuration information for the linked model. The production process models that a user can select as elements of the linked model are the production process models that the user has registered, as well as production process models that other users have registered and that are set to be selectable (i.e., that the user is set to be able to use them).

[0046] The model registration unit 111 may notify the user who registered the linked model into which the production process model is incorporated when the production process model is updated. For example, the model registration unit 111 may send information about the updated production process model (model name, update date and time, update details, etc.) to the user terminal 20 of the user who registered the linked model into which the updated production process model is incorporated.

[0047] <Model acquisition unit 112> The model acquisition unit 112 is configured to acquire a model to be used for inferring a specified manufacturing line (i.e., a model included in the linked model) from among the production process models registered by the model registration unit 111 (i.e., registered in the model database).

[0048] Specifically, the model acquisition unit 112 acquires a front-end model that simulates the front-end process of generating intermediate products from raw materials, and a back-end model that simulates the back-end process of generating final products from intermediate products. The raw materials fed into the front-end model may have already gone through some production process (i.e., products generated in another production process). The final products generated by the back-end model may be products that are fed into yet another production process (i.e., raw materials for another production process). In other words, the "final product" refers only to the product obtained from the back-end process included in the "linked model," and does not refer to the final product of the entire manufacturing line including the back-end process.

[0049] The intermediate products generated in the preceding process correspond to the raw materials in the subsequent process. Therefore, in the inference unit 114 described later, some of the output parameters of the preceding process model (typically some of the product properties) are used as some of the input parameters of the subsequent process model (typically some of the raw material properties).

[0050] The model acquisition unit 112 may acquire the production process model registered by the model registration unit 111 as either a front-end or back-end model. This allows the user to optimize the manufacturing line using the production process model they have prepared. The model acquisition unit 112 may also acquire production process models other than those registered by the user (for example, production process models registered by service providers provided by the information processing system 1) as either front-end or back-end models.

[0051] Furthermore, the model acquisition unit 112 may acquire the first production process model registered by the first user as the upstream process model, and the second production process model registered by the second user as the downstream process model. This makes it possible to optimize a manufacturing line that includes production processes executed by different entities (i.e., production processes executed by multiple users).

[0052] The manufacturing line handled by the information processing system 1 may include three or more production processes. For example, the downstream process may include an intermediate process that generates a secondary intermediate product from an intermediate product, and a final process that generates a final product from the secondary intermediate product. In this case, the model acquisition unit 112 may acquire a upstream process model, an intermediate process model that simulates the intermediate process, and a final process model that simulates the final process. The intermediate process model and the final process model may be production process models registered by the same user, or production process models registered by different users. The model acquisition unit 112 may also acquire a production process model other than the production process model registered by the user (a production process model registered by the service provider) as an intermediate process model or a final process model.

[0053] <Condition acquisition unit 113> The condition acquisition unit 113 is configured to acquire process conditions in both the upstream and downstream process models, which are conditions for the inference unit 114 to perform inference. Specifically, the condition acquisition unit 113 accepts input or selection of each element included in the process conditions of each production process model at the user terminal 20. In addition to process conditions, the condition acquisition unit 113 may also accept input of raw material characteristics for the upstream process model.

[0054] Furthermore, if the subsequent process includes intermediate and final process models, the condition acquisition unit 113 acquires process conditions for the preceding process model, intermediate process model, and final process model, respectively.

[0055] The condition acquisition unit 113 may acquire process conditions adjusted by the condition adjustment unit 116 (described later) instead of the process conditions entered or selected at the user terminal 20.

[0056] <Inference part 114> The inference unit 114 is configured to estimate the values ​​of output parameters in a linked model in which multiple process models are linked. Specifically, the inference unit 114 inputs process conditions into a linked model in which at least a front-end process model and a back-end process model are linked, and obtains at least one of the following as an inferred value: the characteristic value of the intermediate product, the characteristic value of the final product, the state value of the equipment used in the front-end process, and the state value of the equipment used in the back-end process.

[0057] Furthermore, if the subsequent process includes intermediate and final process models, the inference unit 114 may input process conditions into a linked model which is a combination of the preceding process model, the intermediate process model, and the final process model, thereby obtaining at least one of the following as inferred values: characteristic values ​​of the intermediate product, characteristic values ​​of the secondary intermediate product, characteristic values ​​of the final product, state values ​​of the equipment used in the preceding process, state values ​​of the equipment used in the intermediate process, and state values ​​of the equipment used in the final process. This makes it possible to obtain inferred values ​​for each process even for manufacturing lines that include three or more production processes.

[0058] More specifically, the inference unit 114 inputs the characteristic values ​​of the raw materials into the leading production process model of the linked model (i.e., the front-end process model), and inputs the respective process conditions acquired by the condition acquisition unit 113 into each production process model (front-end and back-end process models) that make up the linked model, thereby causing each production process to output inferred values ​​(characteristic values ​​of the product and / or state values ​​of the equipment).

[0059] Furthermore, the number and types of process condition elements differ for each production process. Similarly, the number and types of characteristic values ​​for the generated product and the state values ​​for the equipment also differ for each production process.

[0060] The inference unit 114 can input process conditions into the linked model to obtain inferred values ​​for the characteristics of the final product, the state values ​​of the equipment used in the preceding process, and the state values ​​of the equipment used in the subsequent process. This allows the quality of the product obtained from the manufacturing line simulated by the linked model to be estimated, and also allows optimization indicators such as the energy efficiency and consumption costs of the manufacturing line to be estimated based on the state values ​​of the equipment at each process.

[0061] The inference unit 114 can obtain the characteristics of the intermediate product and the status of the equipment used in the upstream process by inputting the characteristics of the raw materials and process conditions into the upstream process model, and obtain the characteristics of the final product and the status of the equipment used in the downstream process by inputting the characteristics of the intermediate product and process conditions into the downstream process model. This allows the execution results of the upstream process model (information on the intermediate product) to be reliably passed to the downstream process model, while inferring the status of the equipment in each process.

[0062] The inference unit 114 may input only some of the elements included in the intermediate product's characteristic values ​​into the post-processing model. In other words, the inference unit 114 does not necessarily have to use all elements of the intermediate product's characteristic values ​​as input parameters for the post-processing model. The post-processing model receives the elements defined as input parameters in the model information of the post-processing model.

[0063] The inference unit 114 does not necessarily have to acquire all of the characteristic values ​​of the intermediate product, the characteristic values ​​of the final product, the status values ​​of the equipment used in the preceding process, and the status values ​​of the equipment used in the subsequent process. For example, the inference unit 114 may acquire only the characteristic values ​​of the final product, or it may acquire only the status values ​​of the equipment used in the preceding process and the status values ​​of the equipment used in the subsequent process.

[0064] The inference unit 114 records the inferred values ​​(such as the characteristic values ​​of the final product) obtained from the linked model in the model database, for example, by linking them to the linked model on which the inference was performed. The inference unit 114 also displays the inferred values ​​on the user terminal 20. This allows the user to check each inferred value on the user terminal 20.

[0065] Figure 5 schematically illustrates the input and output of information in a linked model that connects the front-end and back-end models. As shown in Figure 5, the front-end model PM1 receives characteristic values ​​CV1, which represent the characteristics of the raw materials, and process conditions PC1 in the front-end process as input parameters. In response to these input parameters, the front-end model PM1 outputs characteristic values ​​CV2, which represent the characteristics of the intermediate product, and state values ​​SV1, which represent the state of the equipment used in the front-end process during or after the front-end process.

[0066] The back-end model PM2, which is linked to the front-end model PM1, receives characteristic values ​​CV2, which represent the characteristics of the intermediate product, and process conditions PC2 in the back-end process as input parameters. In response to these input parameters, the back-end model PM2 outputs characteristic values ​​CV3, which represent the characteristics of the final product, and status values ​​SV2, which represent the state of the equipment used in the back-end process during or after the back-end process.

[0067] <Target acquisition part 115> The target acquisition unit 115 is configured to acquire target values ​​related to the inference values ​​acquired by the inference unit 114. For example, the target acquisition unit 115 receives input and selection of target values ​​from the user terminal 20, links the received target values ​​to a linked model that optimizes process conditions, and registers them in the model database.

[0068] The target value is the objective function used to optimize the process conditions input into the linked model, and is a numerical value that indicates the inferred value itself, or the upper or lower limit (target range) of the evaluation indicator derived from the inferred value. Examples of evaluation indicators include productivity indicators such as manufacturing time, decarbonization indicators such as CO2 emissions, energy conservation indicators such as power consumption and fuel consumption, cost indicators such as manufacturing costs and raw material or fuel consumption efficiency, defect rate indicators such as product yield, and product quality indicators such as product performance stability.

[0069] Productivity indicators, decarbonization indicators, energy saving indicators, and cost indicators are calculated, for example, using the status values ​​of the equipment in each production process and first reference information. The first reference information includes information that shows the correlation between the status values ​​of the equipment in each production process and each indicator. The first reference information includes, for example, calculation formulas, functions, tables, the learning model of the artificial intelligence unit 120, simulators, etc.

[0070] The defect rate index and product quality index are calculated, for example, using the characteristic values ​​of the products from each production process and second reference information. The second reference information includes the correlation between the characteristic values ​​of the products from each production process and each index. The second reference information includes, for example, calculation formulas, functions, tables, the learning model of the artificial intelligence unit 120, simulators, etc.

[0071] Each evaluation index may be calculated using both the state values ​​of the equipment and the characteristic values ​​of the products in each production process, as well as third-party reference information. The third-party reference information includes the correlation between the state values ​​of the equipment and the characteristic values ​​of the products in each production process and each index. The third-party reference information may include, for example, calculation formulas, functions, tables, learning models of the artificial intelligence unit 120, simulators, etc.

[0072] For example, the user can create and input metrics to be used as targets for optimizing the manufacturing line on the user terminal 20, or select metrics from a pre-prepared list of options. The user may set multiple metrics for a single manufacturing line. The user also inputs target values ​​for each metric on the user terminal 20.

[0073] The target acquisition unit 115 may acquire search conditions for optimal process conditions in addition to the target value. The search conditions are input by the user on the user terminal 20. The search conditions include, for example, the elements to be optimized (the optimal value to be searched) from among the elements included in the process conditions of each step, the adjustment range of the elements to be optimized (e.g., the upper and lower limits of the search), the conditions to be set in the fourth reference information described later (e.g., the type of algorithm), the search time, etc.

[0074] When a user optimizes process conditions using a linked model that includes production process models registered by other users, the user can set search conditions for non-confidential elements of the process conditions in those production process models in the same way as the process conditions of the production process models they themselves registered. On the other hand, confidential elements of the process conditions in production process models registered by other users are treated in one of the following ways, as specified by the other user. (1) If the value of a private element is fixed, the value of that private element will not be searched for (and therefore not optimized). (2) If the numerical value of the non-public element can be selected from a pre-prepared list of candidates (numerical values ​​listed in the list), a search (optimization) will be performed within the candidates.

[0075] <Condition Adjustment Unit 116> The condition adjustment unit 116 is configured to adjust the process conditions in the linked model based on the inference values ​​acquired by the inference unit 114, the target values ​​acquired by the target acquisition unit 115, and the fourth reference information. With this configuration, the process conditions of the manufacturing line can be optimized using the linked model based on the target values ​​set by the user.

[0076] The fourth reference information includes the correlation between inferred values ​​and target values ​​and process conditions. The fourth reference information is stored, for example, in the memory unit 12. The fourth reference information is an estimator constructed to take inferred values ​​and target values ​​as input and output process conditions adjusted to achieve the target values. The fourth reference information may include, for example, calculation formulas, functions, tables, simple algorithms, etc., that show the correlation between the combination data of inferred values ​​and target values ​​and process conditions. The correlations included in the fourth reference information can be constructed, for example, by statistically analyzing data that records the process conditions used in the actual production process and measured values ​​such as characteristic values ​​of the product and status values ​​of the equipment observed in the actual production process.

[0077] Furthermore, the fourth reference information may be a search algorithm that searches for the optimal value of each element included in the process conditions. When such a search algorithm is used, the condition adjustment unit 116 adjusts the current process conditions in a direction in which it is predicted that the inferred value will approach the target value according to the search algorithm, and uses the adjusted process conditions (specifically, by having the condition acquisition unit 113 acquire the adjusted process conditions) to have the inference unit 114 update the inferred value. Furthermore, the condition adjustment unit 116 repeats the adjustment of the process conditions and the updating of the inferred value using the updated inferred value. The adjustment of the process conditions is repeated until the search termination condition is met. The search termination condition is, for example, when the difference between the inferred value and the target value reaches less than a threshold, or when the search time set as a search condition has elapsed. The parameters that constitute the search algorithm (branching conditions, judgment conditions, etc.) constitute the correlation of the fourth reference information.

[0078] Furthermore, the fourth reference information may include a condition adjustment model that has been pre-trained to take inferred values ​​and target values ​​as inputs and output process conditions necessary to achieve the target values. In this case, the condition adjustment unit 116 inputs the inferred values ​​and target values ​​into the condition adjustment model included in the artificial intelligence unit 120, and causes the condition adjustment model to output process conditions. The condition adjustment model is constructed, for example, by machine learning using records that associate process conditions used in the past with measured values ​​such as characteristic values ​​of products and status values ​​of equipment observed in the production process as training data. In the condition adjustment model, parameters calculated and tuned through learning constitute the correlation of the fourth reference information.

[0079] The condition adjustment unit 116 does not necessarily have to adjust all elements of the process conditions. For example, the condition adjustment unit 116 may fix the process conditions of some production processes and adjust only the process conditions of other production processes. Alternatively, in each production process, some elements of the process conditions may be fixed and only other elements may be adjusted. The range of process conditions or elements to be adjusted is set, for example, as a search condition.

[0080] The condition adjustment unit 116 records the adjusted process conditions (optimized process conditions) in the model database, for example, by linking them to the optimized linked model. The condition adjustment unit 116 also displays the optimized process conditions and the inferred values ​​and / or target values ​​obtained using those optimized process conditions on the user terminal 20. This allows the user to check the optimized process conditions and the inferred values ​​and / or target values ​​after optimization on the user terminal 20.

[0081] Furthermore, the condition adjustment unit 116 may calculate the contribution rate of each element included in the process conditions to the inferred value and / or target value and display it on the user terminal 20. Examples of such contribution rates include the contribution rate of the temperature sequence of the preceding process to the reduction of the decarbonization index. The contribution rate is calculated or estimated, for example, based on data acquired during the search for optimized process conditions (correlation between each element of the process conditions and the inferred value and / or target value).

[0082] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by each functional unit of the information processing device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0083] The artificial intelligence unit 120 may include learning models such as a Transformer or a language model such as a Recurrent Neural Network (RNN), which may also include a generative AI.

[0084] The language model is an example of a learning model using a machine learning algorithm. Specific machine learning algorithms include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0085] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. Furthermore, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used universally for a wide range of tasks. The trained model included in the artificial intelligence unit 120 can undergo additional training as transfer learning or fine-tuning.

[0086] <Display section 211> The display unit 211 of the user terminal 20 is configured to display the screen shown by the screen data transmitted from the information processing device 10 on the output unit 25.

[0087] <Operation acquisition unit 212> The operation acquisition unit 212 of the user terminal 20 is configured to accept operations from the user of the user terminal 20.

[0088] 3. Information Processing Methods This section describes the information processing method of the information processing device 10. In this information processing method, each part of the information processing device 10 is executed by a computer as a step.

[0089] Specifically, this information processing method comprises a model registration step, a model acquisition step, a condition acquisition step, an inference step, a target acquisition step, and a condition adjustment step. In the model registration step, registration of a model simulating the process of producing a product is accepted. In the model acquisition step, a front-end model simulating the front-end process of producing an intermediate product from raw materials is acquired, and a back-end model simulating the back-end process of producing a final product from the intermediate product is acquired. In the condition acquisition step, process conditions are acquired for both the front-end model and the back-end model. In the inference step, process conditions are input into a linked model, which is a combination of at least the front-end model and the back-end model, to acquire at least one of the following as an inference value: the characteristic value of the intermediate product, the characteristic value of the final product, the state value of the equipment used in the front-end process, and the state value of the equipment used in the back-end process. In the target acquisition step, a target value related to the inference value is acquired. In the condition adjustment step, process conditions are adjusted based on the inference value, the target value, and reference information.

[0090] Figure 6 is an activity diagram showing an example of the flow of information processing (process condition adjustment processing) performed by information processing system 1. The information processing will be explained below in accordance with each activity in this activity diagram.

[0091] The process condition adjustment process begins with the user providing a production process model. The user provides the production process model to the information processing device 10 by uploading it from the user terminal 20 (Activity A110). The information processing device 10 registers the production process model provided from the user terminal 20 (Activity A120).

[0092] After registering the production process model, the user creates a linked model by specifying at least the upstream and downstream process models on the user terminal 20 (Activity A130). The information processing device 10 retrieves the upstream and downstream process models specified on the user terminal 20 from the registered production process models (Activity A140).

[0093] After the linked model is created, the user inputs the initial process conditions and target values ​​on the user terminal 20 (Activity A150). The information processing device 10 retrieves the process conditions and target values ​​input on the user terminal 20 (Activity A160). Subsequently, the information processing device 10 inputs the retrieved process conditions into the linked model and obtains inferred values ​​(such as the characteristics of the final product) (Activity A170).

[0094] After obtaining the inferred values, the information processing device 10 determines whether the termination conditions for process condition adjustment have been met (Activity A180). If the termination conditions have not been met (for example, if the inferred values ​​have not reached the target values), the information processing device 10 adjusts the process conditions using a predetermined algorithm or the like (Activity A190). After adjusting the process conditions, the information processing device 10 re-executes Activity A170, which involves obtaining the inferred values. On the other hand, if the termination conditions have been met, the information processing device 10 outputs the final process conditions and inferred values ​​to the user terminal 20 (Activity A200). As a result, the final process conditions and inferred values ​​are displayed on the user terminal 20 (Activity A210).

[0095] 4. Effect The operation of this embodiment can be summarized as follows: By adjusting the process conditions in the preceding and / or subsequent processes by referring to the inferred values ​​obtained from the linked model, the entire manufacturing line can be optimized.

[0096] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0097] 5. Others In the above embodiment, the information processing device 10 performed various storage and control functions, but instead of the information processing device 10, multiple external devices may be used. That is, various information and programs may be distributed and stored across multiple external devices using blockchain technology or the like.

[0098] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0099] At least one of the devices included in the information processing system 1 may be located outside the country in which the functions of the information processing system 1 are performed.

[0100] The information processing system 1 may consist only of the information processing device 10. In other words, the information processing system 1 does not necessarily have to include a user terminal 20.

[0101] The information processing system 1 does not necessarily have to include a condition adjustment unit 116. For example, the information processing system 1 may be configured so that the user manually searches for the optimal process conditions to obtain a predetermined inference value (target value).

[0102] The product may be provided in any of the following embodiments.

[0103] (1) An information processing system comprising a processor configured to perform the following steps by reading a program, wherein in the model acquisition step, a front-end model simulating a front-end process that produces an intermediate product from raw materials and a back-end model simulating a back-end process that produces a final product from the intermediate product are acquired; in the condition acquisition step, process conditions are acquired in the front-end model and the back-end model, respectively; and in the inference step, at least one of the characteristic values ​​of the intermediate product, the characteristic values ​​of the final product, the state values ​​of the equipment used in the front-end process, and the state values ​​of the equipment used in the back-end process are acquired as inferred values ​​by inputting the process conditions into a linked model in which at least the front-end model and the back-end model are linked.

[0104] (2) An information processing system as described in (1) above, wherein in the inference step, the process conditions are input to the linked model to obtain the characteristic values ​​of the final product, the state values ​​of the equipment used in the preceding process, and the state values ​​of the equipment used in the subsequent process as the inference values.

[0105] (3) An information processing system as described in (2) above, wherein in the inference step, the characteristic values ​​of the intermediate product and the status values ​​of the equipment used in the preceding process are obtained by inputting the characteristic values ​​of the raw materials and the process conditions into the preceding process model, and the characteristic values ​​of the final product and the status values ​​of the equipment used in the subsequent process are obtained by inputting the characteristic values ​​of the intermediate product and the process conditions into the subsequent process model.

[0106] (4) An information processing system according to any one of (1) to (3) above, wherein the post-process includes an intermediate process for generating a secondary intermediate product from the intermediate product and a final process for generating the final product from the secondary intermediate product, the model acquisition step acquires the pre-process model, an intermediate process model that simulates the intermediate process, and a final process model that simulates the final process, the condition acquisition step acquires the process conditions in the pre-process model, the intermediate process model, and the final process model, and the inference step acquires at least one of the characteristic values ​​of the intermediate product, the characteristic values ​​of the secondary intermediate product, the characteristic values ​​of the final product, the state values ​​of the equipment used in the pre-process, the state values ​​of the equipment used in the intermediate process, and the state values ​​of the equipment used in the final process as the inference value by inputting the process conditions into the linked model which is a link between the pre-process model, the intermediate process model, and the final process model, the information processing system.

[0107] (5) An information processing system according to any one of (1) to (4) above, wherein the processor is configured to further perform the following steps: in a target acquisition step, it acquires a target value relating to the inferred value; in a condition adjustment step, it adjusts the process conditions based on the inferred value, the target value, and reference information, wherein the reference information includes the correlation between the inferred value, the target value, and the process conditions.

[0108] (6) An information processing system according to any one of (1) to (5) above, wherein the processor is configured to further perform the following steps: in the model registration step, it accepts the registration of a model that simulates the process of generating a product; and in the model acquisition step, it acquires the model as the pre-process model or the post-process model.

[0109] (7) An information processing system as described in (6) above, wherein in the model registration step, the system accepts the registration of a first model that simulates the process of generating a product from a first user, and the system accepts the registration of a second model that simulates the process of generating a product from a second user, and in the model acquisition step, the system acquires the first model as the pre-process model and the second model as the post-process model.

[0110] (8) An information processing method comprising each step performed by the information processing system described in any one of (1) to (7) above.

[0111] (9) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (7) above. Of course, this is not always the case. [Explanation of symbols]

[0112] 1: Information Processing System 2: Communication lines 10: Information Processing Device 11: Control Unit 12: Storage section 13: Communications Department 14: Communications bus 20: User terminal 21: Control Unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 111: Model Registration Department 112: Model Acquisition Section 113: Condition Acquisition Unit 114: Reasoning part 115:Target acquisition part 116: Condition Adjustment Unit 120: Artificial Intelligence Department 211:Display section 212: Operation acquisition section CV1: Characteristic Value CV2: Characteristic Value CV3: Characteristic Value PC1: Process conditions PC2: Process conditions PM1: Front-end model PM2: Back-end model SV1: Status value SV2: Status value

Claims

1. An information processing system, A processor configured to perform the following steps by reading a program, In the model acquisition step, a front-end model simulating the front-end process of generating an intermediate product from raw materials and a back-end model simulating the back-end process of generating the final product from the intermediate product are acquired. In the condition acquisition step, process conditions are acquired for the preceding process model and the following process model, respectively. An information processing system that, in the inference step, inputs the process conditions into a linked model which is a combination of at least the front-end model and the back-end model, thereby obtaining at least one of the following as an inference value: the characteristic value of the intermediate product, the characteristic value of the final product, the state value of the equipment used in the front-end process, and the state value of the equipment used in the back-end process.

2. In the information processing system described in claim 1, An information processing system that, in the inference step, inputs the process conditions into the linked model to obtain the characteristic values ​​of the final product, the state values ​​of the equipment used in the preceding process, and the state values ​​of the equipment used in the subsequent process as the inference values.

3. In the information processing system described in claim 2, An information processing system that, in the inference step, obtains the characteristic values ​​of the intermediate product and the status values ​​of the equipment used in the preceding process by inputting the characteristic values ​​of the raw materials and the process conditions into the preceding process model, and obtains the characteristic values ​​of the final product and the status values ​​of the equipment used in the subsequent process by inputting the characteristic values ​​of the intermediate product and the process conditions into the subsequent process model.

4. In the information processing system described in claim 1, The aforementioned post-process includes an intermediate process for generating a secondary intermediate product from the intermediate product, and a final process for generating the final product from the secondary intermediate product. In the model acquisition step, the preceding process model, the intermediate process model simulating the intermediate process, and the final process model simulating the final process are acquired. In the condition acquisition step, the process conditions in the preceding process model, the intermediate process model, and the final process model are acquired. An information processing system that, in the inference step, inputs the process conditions into the linked model, which is a combination of the preceding process model, the intermediate process model, and the final process model, thereby obtaining at least one of the following as the inference value: the characteristic value of the intermediate product, the characteristic value of the secondary intermediate product, the characteristic value of the final product, the state value of the equipment used in the preceding process, the state value of the equipment used in the intermediate process, and the state value of the equipment used in the final process.

5. In the information processing system described in claim 1, The aforementioned processor is configured to perform the following steps: In the target acquisition step, the target value related to the inferred value is acquired. In the condition adjustment step, the process conditions are adjusted based on the inferred value, the target value, and the reference information. The aforementioned reference information includes the correlation between the inferred value and the target value and the process conditions in an information processing system.

6. In the information processing system described in claim 1, The aforementioned processor is configured to perform the following steps: In the model registration step, the registration of a model that simulates the process of generating the product is accepted. An information processing system that, in the model acquisition step, acquires the model as either the pre-process model or the post-process model.

7. In the information processing system described in claim 6, In the aforementioned model registration step, the first user registers a first model that simulates the process of generating the product, and the second user registers a second model that simulates the process of generating the product. An information processing system in which, in the model acquisition step, the first model is acquired as the pre-process model and the second model is acquired as the post-process model.

8. Information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 7.

9. It is a program, A program for causing a computer to perform each step of the information processing system described in any one of claims 1 to 7.

Images